TWI600024B - Decoding method,memory storage device and memory control circuit unit - Google Patents

Description

Decoding method, memory storage device and memory control circuit unit

The present invention relates to a decoding technique, and more particularly to a decoding method, a memory storage device, and a memory control circuit unit.

Digital cameras, mobile phones and MP3 players have grown very rapidly in recent years, and the demand for storage media has increased rapidly. Since the rewritable non-volatile memory module (for example, flash memory) has the characteristics of non-volatile data, power saving, small size, and no mechanical structure, it is very suitable for various built-in examples. Portable multimedia device.

In some memory devices, data is encoded before it is stored. Later, when this material needs to be read, the read data will be decoded to try to correct the error. For example, this error may include errors caused by the memory module itself and channel noise generated during the transmission of the data. In general, the power consumption of the decoding circuit is inversely related to the decoding success rate. That is, if the decoding circuit uses a decoding algorithm with a higher decoding success rate and/or complexity, the power consumption for performing decoding is also higher. However, sometimes a simple algorithm can be used to decode and save power. Therefore, how to balance the power consumption of the decoding circuit with the decoding success rate is one of the subjects studied by those skilled in the art.

The invention provides a decoding method, a memory storage device and a memory control circuit unit, which can balance the power consumption of the decoding circuit and the decoding success rate.

An exemplary embodiment of the present invention provides a decoding method for a rewritable non-volatile memory module including a plurality of physical units, the decoding method including: configuring a first message channel and a second message channel in error a check and correction circuit; reading a codeword from a first one of the physical units and evaluating error level information of the codeword; inputting the codeword to the error check via the first message channel And the correction circuit and the error level information of the codeword are input to the error checking and correcting circuit via the second message channel; determining whether the error level information of the codeword meets a preset condition; The error level information of the codeword conforms to the preset condition, input the codeword to a first decoding engine of the error checking and correction circuit, and decode the codeword by the first decoding engine; And if the error level information of the codeword does not meet the preset condition, input the codeword to a second decoding engine of the error checking and correction circuit and by the second solution Engine decode the codeword, wherein the first decoding engine power consumption consumed in a first decoding the second codeword decoding engine is lower than the power consumption consumed in the decoding of said second codeword.

In an exemplary embodiment of the present invention, the step of determining whether the error level information of the codeword meets the preset condition comprises: if the bit error rate is lower than a preset bit error rate, The channel noise strength is lower than the preset channel noise intensity, the number of programming times is lower than the preset number of programming times, the reading times are lower than the preset reading times, and the erasing times are lower than the preset erasing times The number of times, and the sum of the syndromes being lower than the preset one of the preset syndromes is established, and determining that the error level information of the codeword meets the preset condition.

In an exemplary embodiment of the present invention, the step of determining whether the error level information of the codeword meets the preset condition comprises: if the bit error rate is lower than a preset bit error rate, The channel noise strength is lower than the preset channel noise intensity, the number of programming times is lower than the preset number of programming times, the reading times are lower than the preset reading times, and the erasing times are lower than the preset erasing times The number of times and the sum of the syndromes being lower than the plurality of conditions in the preset syndrome combination are determined, and determining that the error level information of the codeword meets the preset condition.

In an exemplary embodiment of the present invention, the step of evaluating the error level information of the codeword includes: performing a parity check operation on the codeword to obtain a plurality of syndromes of the codeword; and accumulating The syndrome is obtained to obtain the syndrome total.

In an exemplary embodiment of the present invention, the decoding method further includes: if the battery power supplied to the error checking and correction circuit is lower than a preset power and the battery power is not coupled to an external charging power source, directly The codeword is input to the first decoding engine and decoded by the first decoding engine.

In an exemplary embodiment of the present invention, the decoding method further includes: if the first decoding engine does not correct all errors in the codeword, decoding the codeword or the first decoding engine The result is input to the second decoding engine.

Another exemplary embodiment of the present invention provides a memory storage device including a connection interface unit, a rewritable non-volatile memory module, and a memory control circuit unit. The connection interface unit is configured to be coupled to a host system. The rewritable non-volatile memory module includes a plurality of physical units. The memory control circuit unit is coupled to the connection interface unit and the rewritable non-volatile memory module, and the memory control circuit unit is configured to configure a first message channel and a second message channel. In the error checking and correcting circuit of the memory control circuit unit, the memory control circuit unit is configured to send a read instruction sequence to instruct to read a codeword from the first physical unit in the physical unit and evaluate the code The error level information of the word, the memory control circuit unit is further configured to input the codeword to the error checking and correcting circuit via the first message channel and to the codeword via the second message channel The error level information is input to the error checking and correcting circuit, and the memory control circuit unit is further configured to determine whether the error level information of the codeword meets a preset condition, if the code word is The error level information is consistent with the preset condition, and the memory control circuit unit is further configured to input the codeword to the first decoding engine of the error checking and correction circuit Decoding the codeword by the first decoding engine, if the error level information of the codeword does not meet the preset condition, the memory control circuit unit is further configured to input the codeword to the Decoding a second decoding engine of the error checking and correction circuit to decode the codeword by the second decoding engine, wherein the first decoding engine consumes a first power consumption in decoding the codeword that is lower than the first The second decoding engine consumes the second power consumption of decoding the codeword.

In an exemplary embodiment of the present invention, the operation of the memory control circuit unit to determine whether the error level information of the codeword meets the preset condition comprises: if the bit error rate is lower than a preset a bit error rate, the channel noise strength is lower than a preset channel noise intensity, the number of stylizations is lower than a preset number of times of programming, the number of readings is lower than a preset number of readings, and the erasing is performed Determining that the number of times is lower than the preset erasure times and the sum of the syndromes is lower than the preset syndrome sub-sum, determining that the error level information of the codeword meets the preset condition .

In an exemplary embodiment of the present invention, the operation of the memory control circuit unit to determine whether the error level information of the codeword meets the preset condition comprises: if the bit error rate is lower than a preset a bit error rate, the channel noise strength is lower than a preset channel noise intensity, the number of stylizations is lower than a preset number of times of programming, the number of readings is lower than a preset number of readings, and the erasing is performed Determining that the number of times is lower than the preset erasure times, and the plurality of conditions in the sum of the syndromes are lower than the preset syndrome sum, determining that the error level information of the codeword meets the preset condition .

In an exemplary embodiment of the present invention, the operation of the memory control circuit unit to evaluate the error level information of the codeword includes performing a parity check operation on the codeword to obtain a plurality of the codewords. a syndrome; and accumulating the syndrome to obtain the syndrome sum.

In an exemplary embodiment of the present invention, if the battery power supplied to the memory control circuit unit is lower than the preset power and the battery power is not coupled to the external charging power source, the memory control circuit unit is further used. Directing the codeword to the first decoding engine to decode the codeword by the first decoding engine.

In an exemplary embodiment of the present invention, if the first decoding engine does not correct all errors in the codeword, the memory control circuit unit is further configured to use the codeword or the first decoding engine. A decoding result is input to the second decoding engine.

Another exemplary embodiment of the present invention provides a memory control circuit unit for controlling a rewritable non-volatile memory module including a plurality of physical units, the memory control circuit unit including a host interface and a memory. Interface, error checking and correction circuit and memory management circuit. The host interface is configured to be coupled to a host system. The memory interface is coupled to the rewritable non-volatile memory module. The error checking and correction circuit includes a first decoding engine and a second decoding engine. The memory management circuit is coupled to the host interface, the memory interface, and the error checking and correcting circuit, and the memory management circuit is configured to configure the first message channel and the second message channel in the error In the checking and correcting circuit, the memory management circuit is configured to send a read command sequence to instruct reading a codeword from a first physical unit in the physical unit and evaluate error level information of the codeword, the memory The body management circuit is further configured to input the codeword to the error checking and correcting circuit via the first message channel, and input the error level information of the codeword to the An error checking and correcting circuit, configured to determine whether the error level information of the codeword meets a preset condition, and if the error level information of the codeword meets the preset condition, The error checking and correction circuit is further configured to input the codeword to the first decoding engine and decode the codeword by the first decoding engine, if the error of the codeword The level information does not meet the preset condition, and the error checking and correction circuit is further configured to input the codeword to the second decoding engine and decode the codeword by the second decoding engine, where The first decoding engine consumes a second amount of power consumed in decoding the codeword that is lower than a second amount of power consumed by the second decoding engine to decode the codeword.

In an exemplary embodiment of the present invention, the error level information includes a bit error rate of the codeword, a channel noise strength of a transmission medium for transmitting the codeword, and a program of the first physical unit. At least one of a number of times, a number of readings of the first physical unit, a number of erasures of the first physical unit, and a sum of syndromes of the codeword.

In an exemplary embodiment of the present invention, the operation of the error checking and correction circuit determining whether the error level information of the codeword meets the preset condition comprises: if the bit error rate is lower than a preset a bit error rate, the channel noise strength is lower than a preset channel noise intensity, the number of stylizations is lower than a preset number of times of programming, the number of readings is lower than a preset number of readings, and the erasing is performed Determining that the number of times is lower than the preset erasure times and the sum of the syndromes is lower than the preset syndrome sub-sum, determining that the error level information of the codeword meets the preset condition .

In an exemplary embodiment of the present invention, the operation of the error checking and correction circuit determining whether the error level information of the codeword meets the preset condition comprises: if the bit error rate is lower than a preset a bit error rate, the channel noise strength is lower than a preset channel noise intensity, the number of stylizations is lower than a preset number of times of programming, the number of readings is lower than a preset number of readings, and the erasing is performed Determining that the number of times is lower than the preset erasure times, and the plurality of conditions in the sum of the syndromes are lower than the preset syndrome sum, determining that the error level information of the codeword meets the preset condition .

In an exemplary embodiment of the present invention, the operation of the memory management circuit to evaluate the error level information of the codeword includes performing a parity check operation on the codeword to obtain a plurality of calibrations of the codeword. a tester; and accumulating the syndrome to obtain the syndrome total.

In an exemplary embodiment of the present invention, if the battery power supplied to the memory control circuit unit is lower than the preset power and the battery power is not coupled to the external charging power source, the error checking and correction circuit is used. Directing the codeword to the first decoding engine and decoding the codeword by the first decoding engine.

In an exemplary embodiment of the present invention, if the first decoding engine does not correct all errors in the codeword, the error checking and correction circuit is further configured to use the codeword or the first decoding engine. The decoding result is input to the second decoding engine.

In an exemplary embodiment of the present invention, if the first decoding engine performs a first decoding operation of a low density parity check code based on a bit flip algorithm, the second decoding engine is based on a gradient falling bit flip algorithm. And a minimum total ensemble algorithm or a total product algorithm performs a second decoding operation of the low density parity check code, if the first decoding engine performs the low density parity check code based on the gradient falling bit flip algorithm The first decoding operation, the second decoding engine performing the second decoding operation of the low density parity check code based on the minimum total ensemble algorithm or the aggregate product algorithm, if the A decoding engine performs the first decoding operation of the low density parity check code based on the minimum total collocation algorithm, and the second decoding engine performs the low density parity check code based on the aggregate product algorithm The second decoding operation.

Based on the above, after obtaining the codeword to be decoded, the error level information of the codeword is evaluated and used as a decoding engine with lower power consumption and lower decoding success rate or using higher power consumption and decoding success. The decoding engine, which also has a higher rate, decodes the reference of this codeword. Thereby, the present invention can strike a balance between the power consumption of the decoding circuit and the decoding success rate.

The above described features and advantages of the invention will be apparent from the following description.

In general, a memory storage device (also referred to as a memory storage system) includes a rewritable non-volatile memory module and a controller (also referred to as a control circuit). Typically, the memory storage device is used with a host system to enable the host system to write data to or read data from the memory storage device.

FIG. 1 is a schematic diagram of a host system, a memory storage device, and an input/output (I/O) device according to an exemplary embodiment of the invention. FIG. 2 is a schematic diagram of a host system, a memory storage device, and an I/O device according to another exemplary embodiment of the present invention.

Referring to FIG. 1 and FIG. 2, the host system 11 generally includes a processor 111, a random access memory (RAM) 112, a read only memory (ROM) 113, and a data transmission interface 114. The processor 111, the random access memory 112, the read-only memory 113, and the data transmission interface 114 are all coupled to the system bus 110.

In the exemplary embodiment, the host system 11 is coupled to the memory storage device 10 through the data transmission interface 114. For example, the host system 11 can store data to or from the memory storage device 10 via the data transfer interface 114. In addition, the host system 11 is coupled to the I/O device 12 through the system bus bar 110. For example, host system 11 can transmit output signals to or receive input signals from I/O device 12 via system bus 110.

In the present exemplary embodiment, the processor 111, the random access memory 112, the read-only memory 113, and the data transfer interface 114 may be disposed on the motherboard 20 of the host system 11. The number of data transmission interfaces 114 may be one or more. The motherboard 20 can be coupled to the memory storage device 10 via a data transmission interface 114 via a wired or wireless connection. The memory storage device 10 can be, for example, a flash drive 201, a memory card 202, a solid state drive (SSD) 203, or a wireless memory storage device 204. The wireless memory storage device 204 can be, for example, a Near Field Communication (NFC) memory storage device, a wireless fax (WiFi) memory storage device, a Bluetooth memory storage device, or a low power Bluetooth memory. A memory storage device based on various wireless communication technologies, such as a storage device (for example, iBeacon). In addition, the motherboard 20 can also be coupled to the Global Positioning System (GPS) module 205, the network interface card 206, the wireless transmission device 207, the keyboard 208, the screen 209, the speaker 210, etc. through the system bus bar 110. I/O device. For example, in an exemplary embodiment, the motherboard 20 can access the wireless memory storage device 204 via the wireless transmission device 207.

In an exemplary embodiment, the host system referred to is any system that can substantially cooperate with a memory storage device to store data. Although in the above exemplary embodiment, the host system is illustrated by a computer system, FIG. 3 is a schematic diagram of the host system and the memory storage device according to another exemplary embodiment of the present invention. Referring to FIG. 3, in another exemplary embodiment, the host system 31 can also be a digital camera, a video camera, a communication device, an audio player, a video player, or a tablet computer, and the memory storage device 30 can be used for Various non-volatile memory storage devices such as a Secure Digital (SD) card 32, a Compact Flash (CF) card 33, or an embedded storage device 34 are used. The embedded storage device 34 includes an embedded multimedia card (eMMC) 341 and/or an embedded multi-chip package (eMCP) storage device 342, and the like, directly coupling the memory module to the memory module. An embedded storage device on the base of the host system.

FIG. 4 is a schematic block diagram of a memory storage device according to an exemplary embodiment of the invention.

Referring to FIG. 4, the memory storage device 10 includes a connection interface unit 402, a memory control circuit unit 404, and a rewritable non-volatile memory module 406.

The connection interface unit 402 is configured to couple the memory storage device 10 to the host system 11 . In the present exemplary embodiment, the connection interface unit 402 is compatible with the Serial Advanced Technology Attachment (SATA) standard. However, it must be understood that the present invention is not limited thereto, and the connection interface unit 402 may also be a Parallel Advanced Technology Attachment (PATA) standard, Institute of Electrical and Electronic Engineers (IEEE) 1394. Standard, high-speed Peripheral Component Interconnect Express (PCI Express) standard, Universal Serial Bus (USB) standard, SD interface standard, Ultra High Speed-I (UHS-I) interface Standard, Ultra High Speed II (UHS-II) interface standard, Memory Stick (MS) interface standard, MCP interface standard, MMC interface standard, eMMC interface standard, universal flash memory (Universal) Flash Storage, UFS) interface standard, eMCP interface standard, CF interface standard, Integrated Device Electronics (IDE) standard or other suitable standards. The connection interface unit 402 can be packaged in a wafer with the memory control circuit unit 404, or the connection interface unit 402 can be disposed outside a wafer including the memory control circuit unit 404.

The memory control circuit unit 404 is configured to execute a plurality of logic gates or control commands implemented in a hard type or a firmware type and perform data in the rewritable non-volatile memory module 406 according to an instruction of the host system 11. Write, read, and erase operations.

The rewritable non-volatile memory module 406 is coupled to the memory control circuit unit 404 and is used to store data written by the host system 11. The rewritable non-volatile memory module 406 can be a single-level memory cell (SLC) NAND-type flash memory module (ie, one memory cell can store one bit of flash memory) Module), Multi Level Cell (MLC) NAND flash memory module (ie, a flash memory module that can store 2 bits in a memory cell), and complex memory cells ( Triple Level Cell, TLC) NAND flash memory module (ie, a flash memory module that can store 3 bits in a memory cell), other flash memory modules, or other memory with the same characteristics Body module.

Each of the memory cells of the rewritable non-volatile memory module 406 stores one or more bits in response to a change in voltage (hereinafter also referred to as a threshold voltage). Specifically, there is a charge trapping layer between the control gate and the channel of each memory cell. By applying a write voltage to the control gate, the amount of electrons in the charge trapping layer can be changed, thereby changing the threshold voltage of the memory cell. This operation of changing the threshold voltage is also referred to as "writing data to the memory cell" or "stylized memory cell". As the threshold voltage changes, each of the memory cells of the rewritable non-volatile memory module 406 has a plurality of storage states. By applying the read voltage, it can be determined which storage state a memory cell belongs to, thereby obtaining one or more bits stored by the memory cell.

FIG. 5 is a schematic block diagram of a memory control circuit unit according to an exemplary embodiment of the invention.

Referring to FIG. 5, the memory control circuit unit 404 includes a memory management circuit 502, a host interface 504, a memory interface 506, and an error check and correction circuit 508.

The memory management circuit 502 is used to control the overall operation of the memory control circuit unit 404. Specifically, the memory management circuit 502 has a plurality of control commands, and when the memory storage device 10 operates, such control commands are executed to perform operations such as writing, reading, and erasing of data. The operation of the memory management circuit 502 will be described below, which is equivalent to the operation of the memory control circuit unit 404.

In the present exemplary embodiment, the control instructions of the memory management circuit 502 are implemented in a firmware version. For example, the memory management circuit 502 has a microprocessor unit (not shown) and a read-only memory (not shown), and such control instructions are programmed into the read-only memory. When the memory storage device 10 is in operation, such control commands are executed by the microprocessor unit to perform operations such as writing, reading, and erasing data.

In another exemplary embodiment, the control command of the memory management circuit 502 can also be stored in a specific area of the rewritable non-volatile memory module 406 (for example, the memory module is dedicated to storing system data). In the system area). In addition, the memory management circuit 502 has a microprocessor unit (not shown), a read-only memory (not shown), and a random access memory (not shown). In particular, the read-only memory has a boot code, and when the memory control circuit unit 404 is enabled, the microprocessor unit first executes the boot code to store the rewritable non-volatile memory. The control commands in the body module 406 are loaded into the random access memory of the memory management circuit 502. After that, the microprocessor unit will run these control commands to perform data writing, reading and erasing operations.

In addition, in another exemplary embodiment, the control command of the memory management circuit 502 can also be implemented in a hardware format. For example, the memory management circuit 502 includes a microcontroller, a memory cell management circuit, a memory write circuit, a memory read circuit, a memory erase circuit, and a data processing circuit. The memory cell management circuit, the memory write circuit, the memory read circuit, the memory erase circuit and the data processing circuit are coupled to the microcontroller. The memory cell management circuit is used to manage the memory cells of the rewritable non-volatile memory module 406 or a group thereof. The memory write circuit is used to issue a write command sequence to the rewritable non-volatile memory module 406 to write data into the rewritable non-volatile memory module 406. The memory read circuit is configured to issue a read command sequence to the rewritable non-volatile memory module 406 to read data from the rewritable non-volatile memory module 406. The memory erase circuit is used to issue an erase command sequence to the rewritable non-volatile memory module 406 to erase data from the rewritable non-volatile memory module 406. The data processing circuit is configured to process data to be written to the rewritable non-volatile memory module 406 and data read from the rewritable non-volatile memory module 406. The write command sequence, the read command sequence, and the erase command sequence may each include one or more code codes or instruction codes and are used to instruct the rewritable non-volatile memory module 406 to perform corresponding writes and reads. Take the erase and other operations. In an exemplary embodiment, the memory management circuit 502 can also provide other types of instruction sequences to the rewritable non-volatile memory module 406 to indicate that the corresponding operations are performed.

The host interface 504 is coupled to the memory management circuit 502 and is configured to receive and identify instructions and data transmitted by the host system 11. That is to say, the instructions and data transmitted by the host system 11 are transmitted to the memory management circuit 502 through the host interface 504. In the present exemplary embodiment, host interface 504 is compatible with the SATA standard. However, it must be understood that the present invention is not limited thereto, and the host interface 504 may be compatible with the PATA standard, the IEEE 1394 standard, the PCI Express standard, the USB standard, the SD standard, the UHS-I standard, the UHS-II standard, and the MS standard. , MMC standard, eMMC standard, UFS standard, CF standard, IDE standard or other suitable data transmission standard.

The memory interface 506 is coupled to the memory management circuit 502 and is used to access the rewritable non-volatile memory module 406. That is, the data to be written to the rewritable non-volatile memory module 406 is converted to a format acceptable to the rewritable non-volatile memory module 406 via the memory interface 506. Specifically, if the memory management circuit 502 is to access the rewritable non-volatile memory module 406, the memory interface 506 will transmit a corresponding sequence of instructions. For example, the sequences of instructions may include a sequence of write instructions indicating write data, a sequence of read instructions indicating read data, a sequence of erase instructions indicating erased material, and instructions for indicating various memory operations (eg, changing read The corresponding instruction sequence that takes the voltage level or performs a garbage collection procedure, etc.). These sequences of instructions are generated, for example, by the memory management circuit 502 and transmitted to the rewritable non-volatile memory module 406 via the memory interface 506. These sequences of instructions may include one or more signals or data on the bus. These signals or materials may include instruction codes or code. For example, in the read command sequence, information such as the read identification code, the memory address, and the like are included.

The error checking and correction circuit 508 is coupled to the memory management circuit 502 and is used to perform error checking and correcting operations to ensure the correctness of the data. Specifically, when the memory management circuit 502 receives a write command from the host system 11, the error check and correction circuit 508 generates a corresponding error correcting code (ECC) for the data corresponding to the write command. And/or error detecting code (EDC), and the memory management circuit 502 writes the data corresponding to the write command and the corresponding error correction code and/or error check code to the rewritable non-volatile In the memory module 406. Thereafter, when the memory management circuit 502 reads the data from the rewritable non-volatile memory module 406, the error correction code and/or the error check code corresponding to the data are simultaneously read, and the error check and correction circuit 508 An error check and correction operation is performed on the read data based on the error correction code and/or the error check code.

In an exemplary embodiment, the memory control circuit unit 404 further includes a buffer memory 510 and a power management circuit 512.

The buffer memory 510 is coupled to the memory management circuit 502 and is used to temporarily store data and instructions from the host system 11 or data from the rewritable non-volatile memory module 406. The power management circuit 512 is coupled to the memory management circuit 502 and is used to control the power of the memory storage device 10.

FIG. 6 is a schematic diagram of managing a rewritable non-volatile memory module according to an exemplary embodiment of the invention. It must be understood that when the operation of the physical unit of the rewritable non-volatile memory module 406 is described in the following exemplary embodiments, the operation of the physical unit with the words "grouping" is a logical concept. That is, the actual location of the physical unit of the rewritable non-volatile memory module 406 is not changed, but the physical unit of the rewritable non-volatile memory module 406 is logically operated.

In the present exemplary embodiment, the memory cells of the rewritable non-volatile memory module 406 constitute a plurality of physical stylized units, and the physical stylized units constitute a plurality of physical erasing units. Specifically, the memory cells on the same word line form one or more entity stylized units. If each memory cell can store more than 2 bits, the entity stylized units on the same word line can be classified into at least a lower entity stylized unit and an upper physical stylized unit. For example, a Least Significant Bit (LSB) of a memory cell belongs to a lower entity stylized unit, and a Most Significant Bit (MSB) of a memory cell belongs to an upper entity stylized unit. In general, in MLC NAND flash memory, the write speed of the lower stylized unit will be greater than the write speed of the upper stylized unit, and / or the reliability of the lower stylized unit is higher than the upper The reliability of the entity stylized unit.

In this exemplary embodiment, the physical stylized unit is the smallest unit that is stylized. That is, the entity stylized unit is the smallest unit that writes data. For example, an entity stylized unit is a physical page or a sector. If the entity stylized unit is a physical page, then the entity stylized units typically include a data bit area and a redundancy bit field. The data bit area contains a plurality of physical fans for storing user data, and the redundant bit area is used for storing system data (for example, error correction codes). In this exemplary embodiment, the data bit area includes 32 physical fans, and one physical fan has a size of 512 bytes (byte, B). However, in other exemplary embodiments, the data bit area may also contain 8, 16, or a greater or lesser number of solid fans, and the size of each of the physical fans may also be larger or smaller. On the other hand, the physical erase unit is the smallest unit of erase. That is, each physical erase unit contains one of the smallest number of erased memory cells. For example, the physical erase unit is a physical block.

Referring to FIG. 6, the memory management circuit 502 logically groups the physical units 610(0)-610(B) of the rewritable non-volatile memory module 406 into a storage area 601 and a replacement area 602. The physical units 610(0)-610(A) in the storage area 601 are used to store data, and the physical units 610(A+1)~610(B) in the replacement area 602 are used to replace the storage area 601. Damaged physical erase unit. In the present exemplary embodiment, each of the physical units 610(0)-610(B) refers to one or more physical erasing units. However, in another exemplary embodiment, each of the physical units 610(0)-610(B) refers to one or more entity stylized units or is comprised of any number of memory cells.

The memory management circuit 502 configures the logic units 612(0)-612(C) to map the physical units 610(0)-610(A) in the storage area 601. For example, in the present exemplary embodiment, the host system 11 accesses the data in the storage area 601 through a logical address (LA), and therefore, each of the logical units 612(0)-612(C) A logical unit is a logical address. However, in another exemplary embodiment, each of the logic units 612(0)-612(C) may also refer to a logical stylized unit, a logical erase unit, or a plurality of consecutive or discontinuous The logical address consists of. Moreover, each of the logical units 612(0)-612(C) can be mapped to one or more physical units.

The memory management circuit 502 records the mapping relationship (also referred to as a logical-entity mapping relationship) between the logical unit and the physical unit in at least one logical-entity mapping table. When the host system 11 wants to read data from the memory storage device 10 or write data to the memory storage device 10, the memory management circuit 502 can perform data storage for the memory storage device 10 according to the logical-entity mapping table. take.

In the present exemplary embodiment, error checking and correction circuit 508 supports low-density parity-check (LDPC) codes. For example, error checking and correction circuit 508 can utilize low density parity check codes for encoding and decoding. In low density parity check codes, a check matrix (also known as a parity check matrix) is used to define valid codewords. The parity check matrix is labeled as matrix H and one codeword is labeled V. According to the following equation (1), if the multiplication of the parity check matrix H and the code word V is a zero vector, it indicates that the code word V is a valid code word. Operator The matrix representing the modulo 2 (mod 2) is multiplied. In other words, the null space of matrix H contains all valid codewords. However, the present invention does not limit the content of the code word V. For example, the codeword V may also include an error correction code or an error check code generated by any algorithm.

…(1)

In equation (1), the dimension of the matrix H is k - multiply - n ( k-by-n ), and the dimension of the codeword V is 1-multiplied - n , where k and n are both positive integers. The code word V includes a message bit and a parity bit. For example, the codeword V can be represented as [ U P ], where the vector U is composed of message bits and the vector P is composed of parity bits. The dimension of the vector U is 1-multiply-( nk ), and the dimension of the vector P is 1-multiply- k . In an exemplary embodiment, the message bits and parity bits in a codeword are collectively referred to as data bits. For example, codeword V has n data bits, where the length of the message bit is ( nk ) bits and the length of the parity bit is k bits. Therefore, the code rate of the code word V is (nk)/n .

In general, a generation matrix (hereinafter referred to as G ) is used in encoding so that the following equation (2) can be satisfied for any vector U. The dimension in which the matrix G is generated is ( nk )-multiply- n .

…(2)

The codeword V generated by equation (2) is a valid codeword. Therefore, equation (2) can be substituted into equation (1), thereby obtaining the following equation (3).

...(3)

Since the vector U can be an arbitrary vector, the following equation (4) is sure to be satisfied. That is to say, after the parity check matrix H is determined, the corresponding generation matrix G can also be determined.

...(4)

When decoding a codeword V , a parity check operation is performed on the data bits in the codeword V , for example, multiplying the parity check matrix H by the codeword V to generate a vector (hereinafter referred to as S , such as the following equation) (5) shown). If the vector S is a zero vector (i.e., each element in the vector S is zero), it indicates that the decoding is successful and the code word V can be directly output. If the vector S is not zero vector (i.e., at least one element of the vector S is not zero), and said at least one error is not a valid codeword V codeword V in the presence of a codeword.

...(5)

In equation (5), the dimension of the vector S is k - multiply -1, and each element in the vector S is also referred to as a syndrome. If the codeword V is not a valid codeword, the error checking and correction circuit 508 performs a decoding operation to attempt to correct the error in the codeword V.

FIG. 7 is a schematic diagram of a parity check matrix according to an exemplary embodiment of the invention.

Referring to FIG. 7, the dimension of the parity check matrix 700 is k -multiply- n . For example, k is 8, and n is 9. However, the present invention does not limit what the positive integers k and n are. Each row of the parity check matrix 700 also represents a constraint. Taking the first column of the parity check matrix 700 as an example, if a certain codeword is a valid codeword, the third, fifth, eighth, and ninth bit of the codeword is added by modulo 2, and a bit is obtained. Yuan "0". Those of ordinary skill in the art should be able to understand how to encode with the parity check matrix 700, and will not be described again here. In addition, the parity check matrix 700 is only an example matrix, and the parity check matrix actually used can be adjusted according to actual requirements. When the memory management circuit 502 is to store a plurality of bits to the rewritable non-volatile memory module 406, the error checking and correction circuit 508 will ( n - k ) each bit to be stored (ie, The message bit) produces the corresponding k parity bits. Next, the memory management circuit 502 writes the n bits (ie, data bits) as a code word to the rewritable non-volatile memory module 406.

FIG. 8 is a schematic diagram showing a threshold voltage distribution of a memory cell according to an exemplary embodiment of the invention.

Referring to FIG. 8, the horizontal axis represents the threshold voltage of the memory cell, and the vertical axis represents the number of memory cells. For example, Figure 8 is a graph showing the threshold voltage distribution of individual memory cells in a solid stylized unit, where state 810 corresponds to bit "1" and state 820 corresponds to bit "0". If the threshold voltage of a memory cell belongs to state 810, it means that the memory cell stores the bit "1"; conversely, if the threshold voltage of a memory cell belongs to state 820, it means that the memory cell stores the bit. Yuan "0". It is worth mentioning that in the present exemplary embodiment, one state in the threshold voltage distribution corresponds to one bit value (ie, "1" or "0"), and there are two possible threshold voltage distributions of the memory cell. Status (ie, states 810 and 820). However, in other exemplary embodiments, each of the threshold voltage distributions may also correspond to a plurality of bit values (eg, "00", "010", etc.) and the threshold voltage distribution of the memory cells may also have four, Eight or any other state. Moreover, the invention does not limit the bits represented by each state. For example, in another exemplary embodiment of FIG. 8, state 810 may also correspond to bit "0", while state 820 corresponds to bit "1."

In the present exemplary embodiment, when data is to be read from the rewritable non-volatile memory module 406, the memory management circuit 502 sends a read command sequence to the rewritable non-volatile memory module 406. To indicate that the rewritable non-volatile memory module 406 reads data from a physical unit (hereinafter also referred to as a first physical unit). For example, based on the read command sequence, the rewritable non-volatile memory module 406 can use the read voltage 801 of FIG. 8 to read the memory cells in the first physical unit. If the threshold voltage of a certain memory cell is less than the read voltage 801, the memory cell will be turned on and the memory management circuit 502 will read the bit "1". Conversely, if the threshold voltage of a certain memory cell is greater than the read voltage 801, the memory cell will not be turned on and the memory management circuit 502 will read the bit "0".

In the present exemplary embodiment, an overlap region 830 is included between state 810 and state 820. The area of the overlap region 830 is positively correlated with the total number of memory cells whose threshold voltage falls within the overlap region 830. For example, the overlap region 830 indicates that a memory cell stores a bit "1" (belonging to state 810), but its threshold voltage is greater than the applied read voltage 801; in addition, a memory cell should be stored Bit "0" (belongs to state 820), but its threshold voltage is less than the applied read voltage 801. In other words, some of the bits read by the application of the read voltage 801 may have errors. In particular, as the usage time of the memory storage device 10 increases, the area of the overlap region 830 gradually increases, and the read data may contain more and more errors.

In the present exemplary embodiment, after receiving the read data from the rewritable non-volatile memory module 406, the memory management circuit 502 performs a parity check operation to verify whether there is an error in the data. If it is determined that there is an error in the data, the error checking and correction circuit 508 performs a decoding operation to decode the data, thereby attempting to correct the error in the data. For example, both the parity check operation and the decoding operation are performed in units of one codeword. In addition, the error checking and correction circuit 508 can support a bit flipping algorithm, a gradient descent bit flipping algorithm, a min sum algorithm, and a sum product. At least two decoding algorithms in a decoding algorithm of a common low-density parity check code such as an algorithm.

FIG. 9 is a schematic diagram of a parity check operation according to an exemplary embodiment of the present invention.

Referring to FIG. 9, assuming that the material read from the first entity unit contains the codeword 901, in the parity check operation, according to equation (5), the parity check matrix 900 is multiplied by the codeword 901 and a check vector 902 is obtained. (ie, vector S ), where each bit in codeword 901 corresponds to at least one element (ie, a syndrome) in check vector 902. For example, bit V ₀ in codeword 901 (corresponding to the first column in parity check matrix 900) corresponds to syndromes S ₁ , S _{4 ,} and S ₇ ; bit V ₁ (corresponding to parity) The second row in the check matrix 900 is corresponding to the syndromes S ₂ , S ₃ and S ₆ , and so on. If the bit V ₀ is an error bit, at least one of the syndromes S ₁ , S ₄ and S ₇ may be "1". If the bit V ₁ is an error bit, at least one of the syndromes S ₂ , S ₃ and S ₆ may be "1", and so on. If the syndromes S ₀ to S _{7 are} all "0", it means that the code word 901 has a high probability that there is no error bit, so the error checking and correction circuit 508 can directly output the code word 901. However, if the codeword 901 has at least one error bit (ie, at least one of the syndromes S ₀ -S ₇ may be "1"), the error checking and correction circuit 508 decodes the codeword 901, In an attempt to correct the error in codeword 901.

FIG. 10 is a schematic diagram of an error checking and correction circuit according to an exemplary embodiment of the invention.

Referring to FIG. 10, the error checking and correction circuit 508 includes a decision circuit 1010, a decoding engine 1020 (hereinafter also referred to as a first decoding engine), and a decoding engine 1030 (hereinafter also referred to as a second decoding engine). The memory management circuit 502 configures a message channel 1001 (hereinafter also referred to as a first message channel) and a message channel 1002 (hereinafter also referred to as a second message channel) in the error checking and correction circuit 508. For example, the message channel 1001 and the message channel 1002 may be physical line channels or virtual shunt channels that are independent of each other. After obtaining the codeword CW _{0 to be} decoded, the memory management circuit 502 evaluates the error level information SI of the codeword CW ₀ . For example, the error level information SI may be any form of quantitative information and the value of the error level information SI is positively correlated with the total number of error bits that the code word CW ₀ may contain. The memory management circuit 502 inputs the codeword CW ₀ into the error check and correction circuit 508 via the message channel 1001 and inputs the error level information SI into the error check and correction circuit 508 via the message channel 1002. For example, via the message channel 1001, the codeword CW ₀ will be temporarily stored in the register 1012 of the decision circuit 1010, and via the message channel 1002, the error level information SI will be temporarily stored in the register 1014 of the decision circuit 1010.

The decision circuit 1010 also includes at least one processing circuit (not shown). After obtaining the error level information SI, the decision circuit 1010 determines whether the error level information SI meets a predetermined condition. If the error level information SI meets the preset condition, the decision circuit 1010 inputs the codeword CW ₁ to the decoding engine 1020 and decodes the codeword CW ₁ by the decoding engine 1020, wherein the codeword CW _{1 is} identical to the codeword CW ₀ . However, if the error level information SI does not meet the preset condition, the decision circuit 1010 inputs the code word CW ₁ to the decoding engine 1030 and decodes the code word CW ₁ by the decoding engine 1030. After decoding the codeword CW ₁ using the decoding engine 1020 or the decoding engine 1030, if the decoding operation performed is successful (ie, all errors in the codeword CW ₁ are corrected), the codeword CW ₂ is output.

It should be noted that the decoding performance of the decoding engine 1020 is lower than the decoding performance of the decoding engine 1020. For example, the decoding algorithm and/or circuit structure used by the decoding engine 1020 is less complex than the decoding algorithm used by the decoding engine 1030. and / or the complexity of the circuit configuration, and therefore the power consumption in the decoding engine 1020 takes decoded codeword CW ₁ (hereinafter, also referred to as a first power consumption) will consume less than ₁ decoding engine 1030 takes in the decoded codeword CW Power (hereinafter also referred to as the second power consumption). In addition, if the code word CW ₁ contains more bit errors, the decoding engine 1020 decoded code word CW decoding success rate ₁ (hereinafter also referred to as first decoding success rate) will be lower than 1030 decoding engine to decode the code word CW ₁ The decoding success rate (hereinafter also referred to as the second decoding success rate). Or, from another perspective, the decoding performance of the decoding engine 1020 is lower than the decoding performance of the decoding engine 1020. It may also mean that for the same codeword, the total number of error bits that the decoding engine 1020 can correct is less than the decoding. The total number of error bits that engine 1030 can correct.

In other words, based on the error level information SI, the decision circuit 1010 can roughly estimate whether the error bit contained in the code word CW ₀ is more or less. If the error bit included in the codeword CW ₀ has a higher probability of being less, the decision circuit 1010 instructs the decoding engine 1020 to decode the codeword CW ₁ , thereby saving money without significantly reducing the decoding success rate. The power consumption of the decoding operation. Conversely, if the error bit contained in the codeword CW ₀ has a higher probability of being higher, the decision circuit 1010 instructs the decoding engine 1030 to decode the codeword CW ₁ , thereby ensuring that the codeword CW ₁ can be successfully decoded. .

In the present exemplary embodiment, the error level codeword CW ₀ SI information comprises bit error rate code word CW _0, and the noise level for the channel word CW ₀ transmission medium of transmission code, the first physical unit stylized wherein at least one of frequency and reading the first physical unit number, the number of erasing the first physical unit and check sub-codeword CW ₀ of the sum. The bit error rate of the codeword CW ₀ refers to the proportion of the error bit in the codeword CW ₀ (or each codeword read from the first physical unit). The channel noise strength of the transmission medium for transmitting the codeword CW ₀ refers to the channel noise strength of the transmission channel between the memory control circuit unit 404 and the rewritable non-volatile memory module 406. The number of stylizations of the first physical unit means that the first physical unit has been programmed several times. The number of reads of the first physical unit means that the first physical unit has been read several times. The number of erasures of the first physical unit means that the first physical unit is erased several times. The above error level information SI can be obtained by looking up the table. In addition, the sum of syndrome about codeword CW _0, the memory management circuit 502 may execute the code word CW ₀ as in equation (5) checks the parity check operation to obtain a plurality of sub-codewords CW ₀ and this accumulation These syndromes obtain the syndrome sum of the codeword CW ₀ . Taking FIG. 9 as an example, if the codeword 901 is the codeword CW ₀ , the syndrome sum of the codeword CW ₀ can be obtained by accumulating the syndromes S ₀ to S ₇ . For example, if there are P syndromes in the syndromes S ₀ to S ₇ which are "1", the syndrome of the codeword CW ₀ is "P".

Corresponding to the different types of error level information SI, the decision circuit 1010 can perform a corresponding determination to determine whether the error level information SI of the code word CW ₀ meets the preset condition. For example, the decision circuit 1010 can determine whether the obtained bit error rate is lower than a preset bit error rate, whether the obtained channel noise strength is lower than a preset channel noise intensity, and whether the obtained stylized number is Whether the number of times of programming is less than a predetermined number of times, whether the number of readings obtained is lower than a predetermined number of readings, whether the number of erasures obtained is lower than a predetermined number of erasures, and/or the obtained syndrome The sum is lower than the sum of the preset syndromes.

In an exemplary embodiment, as long as any of the above conditions is met, for example, the obtained bit error rate is lower than the preset bit error rate, and the obtained channel noise strength is lower than the preset channel noise strength. The number of stylizations obtained is lower than the preset number of stylizations, the number of reads obtained is lower than the preset number of reads, the number of erases obtained is lower than the preset erase times, or the total number of syndromes obtained is obtained. The lowering of the preset syndromes, the decision circuit 1010 determines that the error level information SI of the codeword CW ₀ meets the preset condition and inputs the codeword CW ₁ to the decoding engine 1020. The reason is that if any of the above conditions is satisfied, there is a high probability that the total number of error bits included in the code word CW ₀ (or the code word CW ₁ ) is small, and thus the decoding engine 1020 is used to execute. The decoding operation is relatively power efficient and has little effect on decoding performance. On the other hand, if all the conditions in the above judgment are not satisfied, for example, the obtained bit error rate is not lower than the preset bit error rate, and the obtained channel noise strength is not lower than the preset channel noise intensity, and obtained. The number of stylizations is not less than the preset number of stylizations, the number of reads obtained is not less than the preset number of reads, the number of erases obtained is not less than the preset erase count, or the total number of syndromes obtained If not less than the preset syndrome sum, the decision circuit 1010 determines that the error level information SI of the codeword CW ₀ does not meet the preset condition and inputs the codeword CW ₁ to the decoding engine 1030. The reason is that if all the conditions in the above judgment are not satisfied, it indicates that there is a high probability that the total number of error bits included in the code word CW ₀ (or the code word CW ₁ ) is large, so the decoding engine 1030 is directly used for execution. The decoding operation is more efficient.

In another exemplary embodiment, only when a plurality of conditions in the above determination are met, for example, the obtained bit error rate is lower than the preset bit error rate and the obtained syndrome sum is lower than the preset. The summation of the syndromes, the decision circuit 1010 determines that the error level information SI of the codeword CW ₀ meets the preset condition and inputs the codeword CW ₁ to the decoding engine 1020. It should be noted that the operation of decoding the codeword CW ₁ using the decoding engine 1020 as long as any one of the determination conditions is satisfied, although restricting the use of the decoding engine 1020 based on the establishment of a plurality of determination conditions reduces the usage rate of the decoding engine 1020 ( Or increasing the usage rate of the decoding engine 1030) to increase the power consumption of the error checking and correction circuit 508 as a whole, but relatively increasing the decoding performance of the error checking and correcting circuit 508 due to the strong decoding capability of the decoding engine 1030 and/or Decoding stability.

In an exemplary embodiment, the remaining battery power of the memory storage device 10 may also be used as a reference for the decoding engine 1020 or the decoding engine 1030. For example, if the battery power supplied to the error checking and correcting circuit 508 (ie, the remaining battery power of the memory storage device 10 itself) is lower than a predetermined power amount and the battery power is not coupled to the external charging power source, the decision circuit 1010 also The codeword CW ₁ is directly input to the decoding engine 1020 to decode the codeword CW ₁ by the decoding engine 1020, and the operation of determining whether the error level information SI of the codeword CW ₀ meets the preset condition is skipped. On the other hand, if the remaining battery power of the memory storage device 10 is higher than the preset power or the remaining battery power of the memory storage device 10 is lower than the preset power, the memory storage device 10 is coupled to the external charging power source. Then, the operation of determining whether the error level information SI of the codeword CW ₀ meets the preset condition can be continuously executed.

In an exemplary embodiment, after decoding the codeword CW ₁ using the decoding engine 1020, if the decoding engine 1020 does not correct all errors in the codeword CW ₁ (ie, the decoding operation performed by the decoding engine 1020 fails), the codeword CW ₀ decoding engine 1020 or the decoding result (i.e., the codeword output from the decoding engine 1020 _{CW. 3)} is to be decoded as a code word CW of ₁ input to the decoding engine 1030, to attempt decoding using a strong ability to decode the initial decoding engine 1030 again The codeword CW ₀ or further decodes the codeword CW ₃ based on the decoding result of the decoding engine 1020. For example, with respect to the initial codeword CW _0, the total number of error bits included in the codeword CW ₃ may be reduced. Therefore, the decoding success rate and/or decoding speed of the decoding engine 1030 decoding codeword CW ₃ may be higher than the decoding success rate and/or decoding speed of the directly decoded codeword CW ₀ .

Table 1 below is used to illustrate several example combinations of decoding algorithms employed by decoding engine 1020 and decoding engine 1030 in various example embodiments. It should be noted that in some exemplary embodiments not mentioned, any combination of decoding algorithms that conform to the above-described characteristics of the decoding engine 1020 and the decoding engine 1030 may also be employed, and the present invention is not limited thereto.  <TABLE border="1" borderColor="#000000" width="_0009"><TBODY><tr><td> Decoding Engine 1020 </td><td> Decoding Engine 1030 </td></tr>< Tr><td> bit flip algorithm </td><td> gradient descent bit flip calculus</td></tr><tr><td> bit flip algorithm </td><td> minimum Total Computation Algorithm</td></tr><tr><td> Bit Flip Algorithm</td><td> Total Product Algorithm</td></tr><tr><td> Gradient Decrement Meta-flip calculation </td><td> minimum total ensemble algorithm</td></tr><tr><td> gradient-decreasing bit flipping </td><td> sum-product algorithm </td>< /tr><tr><td> Minimum Total Computation Algorithm</td><td> Total Product Algorithm</td></tr></TBODY></TABLE> Table 1  

Based on Table 1, in an exemplary embodiment, if the decoding engine 1020 is performing a decoding operation of a low density parity check code based on a bit flip algorithm (hereinafter also referred to as a first decoding operation), the decoding engine 1030 is, for example, based on a gradient. The falling bit flip algorithm, the minimum total merging algorithm or the total product algorithm performs another decoding operation of the low density parity check code (hereinafter also referred to as a second decoding operation); in another exemplary embodiment, if the decoding engine 1020 is a first decoding operation of performing a low density parity check code based on a gradient falling bit flip algorithm, and the decoding engine 1030 is, for example, performing a second decoding operation of the low density parity check code based on a minimum total matching algorithm or a total product multiplication algorithm. Or, in another exemplary embodiment, if the decoding engine 1020 is a first decoding operation that performs a low density parity check code based on a minimum total collocation algorithm, the decoding engine 1030 performs a low density parity check based on, for example, a total product multiplication algorithm. The second decoding operation of the code. Those of ordinary skill in the art should be able to understand how to perform corresponding decoding operations and hardware circuit structures that can support a particular decoding algorithm based on the various decoding algorithms, and will not be described herein.

In an exemplary embodiment, both the first decoding operation performed by decoding engine 1020 and the second decoding operation performed by decoding engine 1030 are hard bit mode decoding. For example, in hard bit mode decoding, each bit in codeword CW ₀ is obtained by reading a memory cell based on a single hard decision voltage. In another example embodiment, the first decoding operation performed by decoding engine 1020 and/or the second decoding operation performed by decoding engine 1030 may also be soft bit mode decoding. For example, in soft bit mode decoding, at least one of the code words CW ₀ is obtained by reading the same memory cell based on a plurality of soft decision voltages such that the code word CW ₀ contains more decoded information. In general, the decoding success rate of soft bit mode decoding is higher than the decoding success rate of hard bit mode decoding.

Moreover, in an exemplary embodiment, the first decoding operation performed by decoding engine 1020 and/or the second decoding operation performed by decoding engine 1030 may also switch between hard bit mode decoding and soft bit mode decoding. For example, in an exemplary embodiment, the first decoding operation performed by the decoding engine 1020 and/or the second decoding operation performed by the decoding engine 1030 are preset using hard bit mode decoding, but the decoding engine 1020 fails to decode. Thereafter, decoding engine 1030 automatically switches to soft bit mode decoding to continue performing the decoding operation. Thereby, the operational flexibility of the error checking and correction circuit can be further increased.

FIG. 11 is a flowchart of a decoding method according to an exemplary embodiment of the present invention.

Referring to FIG. 11, in step S1101, the first message channel and the second message channel are configured in the error checking and correcting circuit. In step S1102, the codeword is read from the first entity unit and the error level information of the codeword is evaluated. In step S1103, the codeword is input to the error checking and correcting circuit via the first message channel and the error level information of the codeword is input to the error checking and correcting circuit via the second message channel. In step S1104, it is determined whether the error level information of the codeword meets a preset condition. If the error level information of the codeword meets the preset condition, the codeword is input to the first decoding engine of the error checking and correction circuit and decoded by the first decoding engine in step S1105. If the error level information of the codeword does not meet the preset condition, in step S1106, the codeword is input to a second decoding engine of the error checking and correction circuit and the codeword is decoded by the second decoding engine. And wherein the first decoding engine consumes a second power consumption in decoding the codeword that is lower than a second power consumption of the second decoding engine in decoding the codeword. In an example embodiment, the first decoding success rate of decoding the codeword by the first decoding engine may be lower than the second decoding success rate of decoding the codeword by the second decoding engine.

However, the steps in Fig. 11 have been described in detail above, and will not be described again here. It should be noted that the steps in FIG. 11 can be implemented as multiple codes or circuits, and the present invention is not limited. In addition, the method of FIG. 11 may be used in combination with the above exemplary embodiments, or may be used alone, and the present invention is not limited thereto.

In summary, after obtaining the codeword to be decoded, the error level information of the codeword is evaluated and used as a decoding engine with lower power consumption and lower decoding success rate or using higher power consumption. A decoding engine with a higher decoding success rate decodes the reference of the codeword. Thereby, the present invention can strike a balance between the power consumption of the decoding circuit and the decoding success rate.

Although the present invention has been disclosed in the above embodiments, it is not intended to limit the present invention, and any one of ordinary skill in the art can make some changes and refinements without departing from the spirit and scope of the present invention. The scope of the invention is defined by the scope of the appended claims.

10‧‧‧Memory storage device 11‧‧‧Host system 110‧‧‧System Bus 111‧‧‧ Processor 112‧‧‧ Random access memory 113‧‧‧Read-only memory 114‧‧‧Data transmission interface 12‧‧‧Input/Output (I/O) devices 20‧‧‧ motherboard 201‧‧‧USB flash drive 202‧‧‧ memory card 203‧‧‧ Solid State Drive 204‧‧‧Wireless memory storage device 205‧‧‧Global Positioning System Module 206‧‧‧Network Interface Card 207‧‧‧Wireless transmission 208‧‧‧ keyboard 209‧‧‧ screen 210‧‧‧ Horn 32‧‧‧SD card 33‧‧‧CF card 34‧‧‧ embedded storage device 341‧‧‧Embedded multimedia card 342‧‧‧Embedded multi-chip package storage device 402‧‧‧Connection interface unit 404‧‧‧Memory Control Circuit Unit 406‧‧‧Reusable non-volatile memory module 502‧‧‧Memory Management Circuit 504‧‧‧Host interface 506‧‧‧ memory interface 508‧‧‧Error checking and correction circuit 510‧‧‧ Buffer memory 512‧‧‧Power Management Circuit 601‧‧‧ storage area 602‧‧‧Replacement area 610(0)~610(B)‧‧‧ entity unit 612(0)~612(C)‧‧‧ Logical unit 700, 900‧‧‧ parity check matrix 801‧‧‧Read voltage 810, 820‧‧‧ state 830‧‧‧Overlapping areas 901‧‧‧ code words 902‧‧‧Check Vector 1001, 1002‧‧‧ message channel 1010‧‧‧ Decision Circuit 1012, 1014‧‧‧ register 1020, 1030‧‧‧ decoding engine S1101‧‧‧ steps (configuring the first message channel and the second message channel in the error checking and correction circuit) S1102‧‧‧ steps (reading the codeword from the first physical unit and evaluating the error level information of the codeword) S1103‧‧‧ steps (putting the codeword into the error checking and correction circuit via the first message channel and Inputting the error level information of the codeword to the error checking and correcting circuit via the second message channel) S1104‧‧‧Step (determining whether the error level information of the codeword meets the preset condition) S1105‧‧‧ Step (Entering the codeword into the first decoding engine of the error checking and correction circuit and by the first decoding engine Decoding the codeword) S1106‧ ‧ steps (the codeword is input to a second decoding engine of the error checking and correction circuit and decoded by the second decoding engine)

FIG. 1 is a schematic diagram of a host system, a memory storage device, and an input/output (I/O) device according to an exemplary embodiment of the invention. FIG. 2 is a schematic diagram of a host system, a memory storage device, and an I/O device according to another exemplary embodiment of the present invention. FIG. 3 is a schematic diagram of a host system and a memory storage device according to another exemplary embodiment of the invention. FIG. 4 is a schematic block diagram of a memory storage device according to an exemplary embodiment of the invention. FIG. 5 is a schematic block diagram of a memory control circuit unit according to an exemplary embodiment of the invention. FIG. 6 is a schematic diagram of managing a rewritable non-volatile memory module according to an exemplary embodiment of the invention. FIG. 7 is a schematic diagram of a parity check matrix according to an exemplary embodiment of the invention. FIG. 8 is a schematic diagram showing a threshold voltage distribution of a memory cell according to an exemplary embodiment of the invention. FIG. 9 is a schematic diagram of a parity check operation according to an exemplary embodiment of the present invention. FIG. 10 is a schematic diagram of an error checking and correction circuit according to an exemplary embodiment of the invention. FIG. 11 is a flowchart of a decoding method according to an exemplary embodiment of the present invention.

S1101‧‧‧ steps (configuring the first message channel and the second message channel in the error checking and correction circuit)

S1102‧‧‧ steps (reading the codeword from the first entity unit and evaluating the error level information of the codeword)

S1103‧‧ ‧ inputting the codeword to the error checking and correcting circuit via the first message channel and inputting the error level information of the codeword to the error checking and correcting circuit via the second message channel

S1104‧‧‧Step (determining whether the error level information of the codeword meets the preset condition)

S1105‧‧‧ Step of inputting the codeword to a first decoding engine of an error checking and correction circuit and decoding the codeword by a first decoding engine

S1106‧ ‧ steps (the codeword is input to a second decoding engine of the error checking and correction circuit and decoded by the second decoding engine)

Claims (24)

A decoding method for a rewritable non-volatile memory module including a plurality of physical units, the decoding method comprising: configuring a first message channel and a second message channel in an error checking and correcting circuit; Transmitting a read command sequence to the rewritable non-volatile memory module via a memory interface, wherein the read command sequence indicates reading a codeword from a first one of the physical units and evaluating An error level information of the codeword; inputting the codeword to the error checking and correction circuit via the first message channel and inputting the error level information of the codeword to the error check and correction via the second message channel a circuit; determining whether the error level information of the codeword meets a preset condition; if the error level information of the codeword meets the preset condition, inputting the codeword to a first decoding of the error checking and correction circuit The engine decodes the codeword by the first decoding engine; and if the error level information of the codeword does not meet the preset condition, the codeword is input to the error check and school a second decoding engine of the circuit and decoding the codeword by the second decoding engine, wherein the first decoding engine consumes a first power consumption in decoding the codeword lower than the second decoding engine consumes the code in decoding a second power consumption of the word, wherein if the error level information of the codeword meets the preset condition, both the first decoding engine and the second decoding engine are capable of successfully decoding the codeword. The decoding method of claim 1, wherein the error level information includes a one-bit error rate of the codeword, a channel noise strength of a transmission medium for transmitting the codeword, and the first physical unit. At least one of a programmed number of times, a number of reads of the first physical unit, an erasing number of the first physical unit, and a syndrome sum of the codeword. The decoding method of claim 2, wherein the step of determining whether the error level information of the codeword meets the preset condition comprises: if the bit error rate is lower than a preset bit error rate, The channel noise strength is lower than a preset channel noise intensity, the number of programming times is lower than a preset number of programming times, the reading times are lower than a preset reading number, and the erasing times are lower than a preset erasing The condition of the number of divisions and the sum of the syndromes being lower than the sum of the preset syndromes is established, and the error level information of the codeword is determined to meet the preset condition. The decoding method of claim 2, wherein the step of determining whether the error level information of the codeword meets the preset condition comprises: if the bit error rate is lower than a preset bit error rate, The channel noise strength is lower than a preset channel noise intensity, the number of programming times is lower than a preset number of programming times, the reading times are lower than a preset reading number, and the erasing times are lower than a preset erasing The number of divisions and the plurality of conditions in the sum of the syndromes being lower than a preset syndrome are determined, and the error level information of the codeword is determined to meet the preset condition. The decoding method of claim 2, wherein the step of evaluating the error level information of the codeword comprises: performing a parity check operation on the codeword to obtain a plurality of syndromes of the codeword; And accumulating the syndromes to obtain the syndrome sum. The decoding method of claim 1, further comprising: if a battery power supplied to the error checking and correction circuit is lower than a predetermined power amount and the battery power is not coupled to an external charging power source, directly The codeword is input to the first decoding engine and decoded by the first decoding engine. The decoding method of claim 1, further comprising: if the first decoding engine does not correct all errors in the codeword, inputting the codeword or a decoding result of the first decoding engine to the first Two decoding engines. The decoding method of claim 1, wherein the second decoding engine is based on a gradient if the first decoding engine performs a first decoding operation of a low density parity check code based on the one-bit flip algorithm. Performing a second decoding operation of the low density parity check code by a falling bit flip algorithm, a minimum total combining algorithm or a total product multiplication algorithm, wherein the first decoding engine executes based on the gradient falling bit flip algorithm The first decoding operation of the low-density parity check code, the second decoding engine performing the second decoding operation of the low-density parity check code based on the minimum total ensemble algorithm or the aggregate product algorithm, wherein the second decoding operation A decoding engine performs the first decoding operation of the low density parity check code based on the minimum total combining algorithm, and the second decoding engine performs the second decoding operation of the low density parity check code based on the aggregate product algorithm. A memory storage device comprising: a connection interface unit for coupling to a host system; a rewritable non-volatile memory module including a plurality of physical units; and a memory control circuit unit coupled to the connection interface unit and the a memory-type non-volatile memory module, wherein the memory control circuit unit is configured to configure a first message channel and a second message channel in an error checking and correcting circuit of the memory control circuit unit, wherein the memory The body control circuit unit is configured to send a read command sequence via a memory interface to instruct reading a codeword from a first one of the plurality of physical units and evaluate an error level information of the codeword, wherein the memory The body control circuit unit is further configured to input the codeword to the error checking and correcting circuit via the first message channel, and input the error level information of the codeword to the error checking and correcting circuit via the second message channel, The memory control circuit unit is further configured to determine whether the error level information of the codeword meets a preset condition, wherein the error of the codeword, etc. The information conforms to the preset condition, and the memory control circuit unit further inputs the codeword to a first decoding engine of the error checking and correction circuit to decode the codeword by the first decoding engine, if the codeword The error level information does not meet the preset condition, and the memory control circuit unit further inputs the codeword to a second decoding engine of the error checking and correction circuit to decode the codeword by the second decoding engine. The first decoding engine consumes a first power consumption lower than decoding the codeword The second decoding engine consumes a second power consumption of the codeword, wherein if the error level information of the codeword meets the preset condition, the first decoding engine and the second decoding engine are capable. The codeword was successfully decoded. The memory storage device of claim 9, wherein the error level information includes a one-dimensional error rate of the codeword, a channel noise strength of a transmission medium for transmitting the codeword, the first At least one of a number of stylizations of the physical unit, a number of reads of the first physical unit, a number of erasures of the first physical unit, and a syndrome sum of the codeword. The memory storage device of claim 10, wherein the memory control circuit unit determines whether the error level information of the codeword meets the preset condition comprises: if the bit error rate is lower than one The default bit error rate, the channel noise strength is lower than a preset channel noise intensity, the stylized number is lower than a preset stylized number, the read count is lower than a preset read count, the wipe The condition that the number of divisions is lower than a predetermined number of erasures and the sum of the syndromes is lower than a preset syndrome is established, and the error level information of the codeword is determined to meet the preset condition. The memory storage device of claim 10, wherein the memory control circuit unit determines whether the error level information of the codeword meets the preset condition comprises: if the bit error rate is lower than one The default bit error rate, the channel noise strength is lower than a preset channel noise intensity, the stylized number is lower than a preset stylized number, the read count is lower than a preset read count, the wipe The number of divisions is less than a preset erasure time The number and the sum of the syndromes are lower than a plurality of conditions in a predetermined syndrome sum, and the error level information of the codeword is determined to meet the preset condition. The memory storage device of claim 10, wherein the operation of the memory control circuit unit to evaluate the error level information of the codeword comprises: performing a parity check operation on the codeword to obtain the codeword a plurality of syndromes; and accumulating the syndromes to obtain the syndrome sum. The memory storage device of claim 9, wherein the memory provided to the memory control circuit unit is lower than a predetermined power amount and the battery power is not coupled to an external charging power source, the memory The body control circuit unit is further configured to directly input the codeword to the first decoding engine to decode the codeword by the first decoding engine. The memory storage device of claim 9, wherein the memory control circuit unit is further configured to decode the codeword or the first decoding if the first decoding engine does not correct all errors in the codeword. A decoding result of the engine is input to the second decoding engine. The memory storage device of claim 9, wherein if the first decoding engine performs a first decoding operation of a low density parity check code based on a one-bit flip algorithm, the second decoding engine is based on Performing a second decoding operation of the low density parity check code by a gradient falling bit flip algorithm, a minimum total combining algorithm or a total product algorithm Wherein if the first decoding engine performs the first decoding operation of the low density parity check code based on the gradient falling bit flip algorithm, the second decoding engine executes based on the minimum total combining algorithm or the aggregate product algorithm The second decoding operation of the low density parity check code, wherein if the first decoding engine performs the first decoding operation of the low density parity check code based on the minimum total collocation algorithm, the second decoding engine is based on the total The second algorithm performs the second decoding operation of the low density parity check code. A memory control circuit unit for controlling a rewritable non-volatile memory module including a plurality of physical units, the memory control circuit unit comprising: a host interface for coupling to a host system; a memory interface for coupling to the rewritable non-volatile memory module; an error checking and correction circuit comprising a first decoding engine and a second decoding engine; and a memory management circuit coupled The memory management circuit is configured to configure a first message channel and a second message channel in the error checking and correcting circuit, wherein the memory interface is configured to connect to the host interface, the memory interface, and the error checking and correcting circuit, wherein the memory The management circuit is configured to send a read command sequence via the memory interface to indicate that a codeword is read from a first one of the physical units and an error level information of the codeword is evaluated, wherein the memory management The circuit is further configured to pass the codeword via the first message channel Inputting to the error checking and correcting circuit and inputting the error level information of the codeword to the error checking and correcting circuit via the second message channel, wherein the error checking and correcting circuit is configured to determine the error level of the codeword Whether the information meets a preset condition, wherein if the error level information of the codeword meets the preset condition, the error checking and correction circuit further inputs the codeword to the first decoding engine and is decoded by the first decoding The engine decodes the codeword. If the error level information of the codeword does not meet the preset condition, the error checking and correction circuit is further configured to input the codeword to the second decoding engine and decode by the second decoding engine. The codeword, wherein the first decoding engine consumes a first power consumption in decoding the codeword is lower than a second power consumption of the second decoding engine in decoding the codeword, wherein if the codeword is If the error level information meets the preset condition, both the first decoding engine and the second decoding engine have the ability to successfully decode the codeword. The memory control circuit unit of claim 17, wherein the error level information includes a one-bit error rate of the codeword, a channel noise strength of a transmission medium for transmitting the codeword, the first At least one of a number of stylizations of a physical unit, a number of reads of the first physical unit, a number of erasures of the first physical unit, and a syndrome sum of the codeword. The memory control circuit unit of claim 18, wherein the error checking and correction circuit determines whether the error level information of the codeword meets the preset condition comprises: If the bit error rate is lower than a preset bit error rate, the channel noise strength is lower than a preset channel noise intensity, the stylized number is lower than a preset stylized number, and the read number is lower than Determining the number of the preset reading times, the number of erasing times is lower than a preset erasing number, and the sum of the syndromes is lower than a predetermined syndrome sum, determining the codeword The error level information conforms to the preset condition. The memory control circuit unit of claim 18, wherein the error checking and correcting circuit determines whether the error level information of the codeword meets the preset condition comprises: if the bit error rate is lower than a preset bit error rate, the channel noise strength is lower than a preset channel noise intensity, the stylized number is lower than a preset stylized number, and the read number is lower than a preset read count, Determining that the number of erasures is less than a preset erasure number, and the plurality of conditions in the sum of the syndromes being lower than a preset syndrome is determined, and determining that the error level information of the codeword meets the preset condition . The memory control circuit unit of claim 18, wherein the memory management circuit evaluates the error level information of the codeword comprises: performing a parity check operation on the codeword to obtain the codeword a plurality of syndromes; and accumulating the syndromes to obtain the syndrome sum. The memory control circuit unit of claim 17, wherein if a battery power supplied to the memory control circuit unit is lower than a predetermined power amount and the battery power is not coupled to an external charging power source, Error check and correction The path is further used to directly input the codeword to the first decoding engine and decode the codeword by the first decoding engine. The memory control circuit unit of claim 17, wherein if the first decoding engine does not correct all errors in the codeword, the error checking and correction circuit is further configured to use the codeword or the first A decoding result of the decoding engine is input to the second decoding engine. The memory control circuit unit of claim 17, wherein the second decoding engine if the first decoding engine performs a first decoding operation of a low density parity check code based on a one-bit flip algorithm Performing a second decoding operation of the low density parity check code based on a gradient falling bit flip algorithm, a minimum total combining algorithm or a total product multiplication algorithm, wherein the first decoding engine flips based on the gradient falling bit The algorithm performs the first decoding operation of the low density parity check code, and the second decoding engine performs the second decoding operation of the low density parity check code based on the minimum total ensemble algorithm or the aggregate product algorithm, wherein If the first decoding engine performs the first decoding operation of the low density parity check code based on the minimum total collocation algorithm, the second decoding engine performs the second of the low density parity check code based on the aggregate product algorithm Decoding operation.